© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 1692
    Prev
    Next
    INDEX
    Explanations

    instances of the word "today" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ses
    -0.08
    ic
    -0.07
    s
    -0.06
    leaf
    -0.06
    ÙĦاÙģ
    -0.06
     Month
    -0.06
    isto
    -0.06
    aphael
    -0.06
    ised
    -0.06
    ely
    -0.06
    POSITIVE LOGITS
    aday
    0.11
    lerde
    0.10
    arrow
    0.08
    -day
    0.07
    'hui
    0.07
    ÏĥÏĩ
    0.07
    eÄį
    0.07
    jÅ¡ÃŃ
    0.07
    ONTAL
    0.07
    redient
    0.07
    Activations Density 0.032%

    No Known Activations